S
Shalabh Bhatnagar
Researcher at Indian Institute of Science
Publications - 308
Citations - 5153
Shalabh Bhatnagar is an academic researcher from Indian Institute of Science. The author has contributed to research in topics: Stochastic approximation & Markov decision process. The author has an hindex of 30, co-authored 294 publications receiving 4300 citations. Previous affiliations of Shalabh Bhatnagar include University of Marne-la-Vallée & Indian Institutes of Technology.
Papers
More filters
Journal ArticleDOI
Successive Over Relaxation Q-Learning
TL;DR: This letter derives a modified fixed point iteration for SOR Q -values and utilize stochastic approximation to derive a learning algorithm to compute the optimal value function and an optimal policy and shows that SORQ -learning is faster compared to the standard Q -learning algorithm.
Proceedings ArticleDOI
Stochastic Approximation Trackers for Model-Based Search
TL;DR: The algorithms fundamentally track the well-known derivative-free model-based search methods in an efficient and resourceful manner with additional heuristics to accelerate the scheme.
Posted Content
Asymptotic and non-asymptotic convergence properties of stochastic approximation with controlled Markov noise using lock-in probability
TL;DR: A lower bound on the lock-in probability of such frameworks i.e. the probability of convergence to a specific attractor of the o.i.d.d noise is given given that the iterates visit its domain of attraction after a sufficiently large number of iterationsn0.
Proceedings Article
A Markov Decision Process Framework for Predictable Job Completion Times on Crowdsourcing Platforms
TL;DR: In this work, an instance of the pricing problem is studied and a solution based on the framework of Markov Decision Processes (MDPs) is proposed.
Book ChapterDOI
Pattern Synthesis for Large-Scale Pattern Recognition
TL;DR: This work proposes a novel and unified solution for these problems by deriving a compact and generalized abstraction of the data that reduces the computational requirements, and its generalization reduces the curse of dimensionality effect.